We investigate whether aphasia predictions are improved by examining interactions between a common genetic polymorphism (BDNF) and MEPs pre- and post-cTBS. Subjects were 19 adults with chronic aphasia subsequent to a left-hemisphere ischemic stroke. We collected MEPs pre- and post-cTBS to motor cortex and obtained saliva samples. We evaluated the extent to which BDNF ValMet polymorphism interacted with pre-cTBS cortical excitability, and cTBS-induced MEP-suppression to predict WAB-AQ. These predictors were added to established predictors of age at stroke, lesion volume, and log-transformed time post-stroke. We fit a backward stepwise linear regression model with these factors. While controlling for the effects of time post-stroke and total lesion volume, BDNF genotype showed a main effect such that when all other factors are average, ValVal carriers showed better language recovery than Met carriers. Furthermore, BDNF genotype interacted with each predictor of interest: age at stroke, baseline MEP, and change in MEP. First, increased age at stroke was associated with lower WAB-AQ for both groups, but had a stronger effect for ValVal carriers than ValMet carriers. This effect was driven by a significant difference for individuals who were younger but not older at CVA. Second, cortical excitability was positively associated with WAB-AQ for ValVal carriers, but negatively associated with WAB-AQ for ValMet carriers. Third, ValMet carriers with lower WAB-AQ showed increased paradoxical responses to cTBS, whereas cTBS-induced changes in MEP-suppression was not associated with variability in severity for ValVal carriers. Neurophysiological indicators and genetic biomarkers of neuroplasticity improve ability to predict post-stroke language recovery. These findings provide novel insights into mechanisms of variability in stroke recovery and may improve aphasia prognostics.